Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part II Edward D. Barker, Ph.D. Social, Genetic, and Developmental Psychiatry.

Slides:



Advertisements
Similar presentations
Simple linear models Straight line is simplest case, but key is that parameters appear linearly in the model Needs estimates of the model parameters (slope.
Advertisements

Latent Growth Modeling Chongming Yang Research Support Center FHSS College.
G ROWTH M IXTURE M ODELING Shaunna L. Clark & Ryne Estabrook Advanced Genetic Epidemiology Statistical Workshop October 24,
Introduction to Research Design Statlab Workshop, Fall 2010 Jeremy Green Nancy Hite.
6-1 Introduction To Empirical Models 6-1 Introduction To Empirical Models.
Simple Linear Regression 1. Correlation indicates the magnitude and direction of the linear relationship between two variables. Linear Regression: variable.
Latent Growth Curve Modeling In Mplus:
Binary Response Lecture 22 Lecture 22.
Fall 2006 – Fundamentals of Business Statistics 1 Chapter 13 Introduction to Linear Regression and Correlation Analysis.
David Kaplan & Heidi Sweetman University of Delaware Two Methodological Perspectives on the Development of Mathematical Competencies in Young Children:
Linear Regression and Correlation Analysis
Factor Analysis Ulf H. Olsson Professor of Statistics.
Chapter 13 Introduction to Linear Regression and Correlation Analysis
Notes on Logistic Regression STAT 4330/8330. Introduction Previously, you learned about odds ratios (OR’s). We now transition and begin discussion of.
An Introduction to Logistic Regression
Correlation and Regression Analysis
FINAL REPORT: OUTLINE & OVERVIEW OF SURVEY ERRORS
Introduction to Regression Analysis, Chapter 13,
Statistical hypothesis testing – Inferential statistics II. Testing for associations.
Mixture Modeling Chongming Yang Research Support Center FHSS College.
Introduction to Multilevel Modeling Using SPSS
Multilevel Modeling: Other Topics
Regression and Correlation Methods Judy Zhong Ph.D.
Xitao Fan, Ph.D. Chair Professor & Dean Faculty of Education University of Macau Designing Monte Carlo Simulation Studies.
Inference for regression - Simple linear regression
Trajectory 1. Physics. The path of any body moving under the action of given forces... especially the curve described by a projectile in its flight through.
1 Least squares procedure Inference for least squares lines Simple Linear Regression.
Categorical and Zero Inflated Growth Models Alan C. Acock* Summer, 2009 *Alan C. Acock, Department of Human Development and Family Sciences, Oregon State.
Social patterning in bed-sharing behaviour A longitudinal latent class analysis (LLCA)
Growth Mixture Modeling of Longitudinal Data David Huang, Dr.P.H., M.P.H. UCLA, Integrated Substance Abuse Program.
April 6 Logistic Regression –Estimating probability based on logistic model –Testing differences among multiple groups –Assumptions for model.
Multilevel Linear Models Field, Chapter 19. Why use multilevel models? Meeting the assumptions of the linear model – Homogeneity of regression coefficients.
The relationship between error rates and parameter estimation in the probabilistic record linkage context Tiziana Tuoto, Nicoletta Cibella, Marco Fortini.
Regression. Population Covariance and Correlation.
Measurement Models: Exploratory and Confirmatory Factor Analysis James G. Anderson, Ph.D. Purdue University.
Research Seminars in IT in Education (MIT6003) Quantitative Educational Research Design 2 Dr Jacky Pow.
Business Statistics: A Decision-Making Approach, 6e © 2005 Prentice-Hall, Inc. Chap 13-1 Introduction to Regression Analysis Regression analysis is used.
Multilevel Modeling: Other Topics David A. Kenny January 7, 2014.
Latent Growth Modeling Byrne Chapter 11. Latent Growth Modeling Measuring change over repeated time measurements – Gives you more information than a repeated.
Political Science 30: Political Inquiry. Linear Regression II: Making Sense of Regression Results Interpreting SPSS regression output Coefficients for.
Roghayeh parsaee  These approaches assume that the study sample arises from a homogeneous population  focus is on relationships among variables 
Copyright © 2010 Pearson Education, Inc Chapter Seventeen Correlation and Regression.
University Rennes 2, CRPCC, EA 1285
Logistic Regression Analysis Gerrit Rooks
Exploring social mobility with latent trajectory group analysis Patrick Sturgis, University of Southampton and National Centre for Research Methods From.
Two-Group Discriminant Function Analysis. Overview You wish to predict group membership. There are only two groups. Your predictor variables are continuous.
ANCOVA.
Maths Study Centre CB Open 11am – 5pm Semester Weekdays
Quantitative Methods. Bivariate Regression (OLS) We’ll start with OLS regression. Stands for  Ordinary Least Squares Regression. Relatively basic multivariate.
The Probit Model Alexander Spermann University of Freiburg SS 2008.
Growth mixture modeling
Stats Methods at IC Lecture 3: Regression.
Predicting Energy Consumption in Buildings using Multiple Linear Regression Introduction Linear regression is used to model energy consumption in buildings.
An Introduction to Latent Curve Models
BINARY LOGISTIC REGRESSION
Psych 706: stats II Class #4.
Probability Theory and Parameter Estimation I
Linear Regression.
Multiple Regression Prof. Andy Field.
Notes on Logistic Regression
Political Science 30: Political Inquiry
Multiple logistic regression
Limitations of Hierarchical and Mixture Model Comparisons
Ass. Prof. Dr. Mogeeb Mosleh
Logistic Regression.
Introduction to Logistic Regression
Day 2 Applications of Growth Curve Models June 28 & 29, 2018
Latent Variable Mixture Growth Modeling in Mplus
Concepts and Applications of Kriging
Rachael Bedford Mplus: Longitudinal Analysis Workshop 23/06/2015
Presentation transcript:

Latent Growth Curve Modeling In Mplus: An Introduction and Practice Examples Part II Edward D. Barker, Ph.D. Social, Genetic, and Developmental Psychiatry Centre Institute of Psychiatry, King’s College London

Outline  Basic unconditional GMM  Introduction  Mplus code  Output and graphs  Conditional GMM (predictor)  Introduction  Mplus code  Output  Class-specific variance?  Introduction  Mplus code  Output and graphs  Exporting probabilities  Save from Mplus  Import to SPSS  Transpose file  Merge with data file  Run “weighted” frequency  Practice: 1 to 6 traj solutions

General Mixture Models  Latent growth curve models examine individual variation around a single mean growth curve  What we have been examining up to now  Growth Mixture models relaxes this assumption  Population may consist of a mixture of distinct subgroups defined by their developmental trajectories  Heterogeneity in developmental trajectories  Each of wich may represent distinct etiologies and/or outcomes

When are GMMs appropriate?  Populations contain individuals with normative growth trajectories as well as individuals with non-normative growth  Delinquent behaviors and early onset vs. late onset distinction (Moffitt, 1993)  Different factors may predict individual variation within the groups as well as distal outcomes of the growth processes  May want different interventions for individuals in different subgroups on growth trajectories. We could focus interventions on individuals in non- normative growth directories that have undesirable consequences.

Deciding on number of classes  Muthén, 2004  Estimate 1 to 6 trajectory solutions (Familiar with EFAs?)  Compared fit indices (to be covered)  Add trajectory specific variation to models  Model fit and classification accuracy improves  Important: usefulness of the latent classes (Nagin, 2005)  Check to make sure the trajectories make sense from your data  Do they validate?  NO? Is this related to age-range, predictors, outcomes, covariates?  Look at early publications with 6-7 trajectories....

Deciding on number of classes  Bayesian Information Criterion  BIC = -2logL + p ln n  where p is number of free parameters (15)  n is sample size (1102)  -2( ) + 15(log(1102)) =  smaller is better, pick solution that minimizes BIC

Deciding on number of classes  Entropy  This is a measure of how clearly distinguishable the classes are based on how distinctly each individual’s estimated class probability is.  If each individual has a high probability of being in just one class, this will be high.  It ranges from zero to one with values close to one indicating clear classification.

Deciding on number of classes  Lo, Mendell, and Rubin likelihood ratio test (LMR-LRT)  Tests class K is better fit to data compared to K-1 class  2 vs. 1; 3 vs 2; 4 vs 3, etc.

GMM: Muthén & Muth é n, 2000 Intercept Slope D12D13D14D15D16D C

GMM: Nagin variety Intercept Slope D12D13D14D15D16D C

GMM: Nagin variety

GMM: Selected output

GMM: Starting values

Practice 1  Run basic GMM  Write Mplus code  Annotate output  View graph of estimate and observed trajectories  Get starting values (write them down)  Change basic GMM code  Include starting values  Re-run and examine trajectories

Outline  Basic unconditional GMM  Introduction  Mplus code  Output and graphs  Conditional GMM (predictor)  Introduction  Mplus code  Output  Class-specific variance?  Introduction  Output and graphs  Exporting probabilities  Save from Mplus  Import to SPSS  Transpose file  Merge with data file  Run “weighted” frequency  Practice: 1 to 6 traj solutions

GMM: Conditional

Conditional: Selected output

Starting values for conditional

Practice 2  Run Conditional GMM without starting values  Annotate output  View graph of estimated and observed trajectories  Run Conditional GMM with starting values  Get starting values from basic GMM model  Annotate output  View graph of observed and estimated trajectories  Question: do starting values always work?

Outline  Basic unconditional GMM  Introduction  Mplus code  Output and graphs  Conditional GMM (predictor)  Introduction  Mplus code  Output  Class-specific variance?  Introduction  Output and graphs  Exporting probabilities  Save from Mplus  Import to SPSS  Transpose file  Merge with data file  Run “weighted” frequency

Class specific variance

Class specific variance: Selected output

Starting values: Selected output

Practice 3  Run basic GMM  Rename and add class specific variance  Annotate output to note changes  Run again  Use starting values from original model

Outline  Basic unconditional GMM  Introduction  Mplus code  Output and graphs  Conditional GMM (predictor)  Introduction  Mplus code  Output  Class-specific variance?  Introduction  Output and graphs  Exporting probabilities  Transpose file  Merge with data file  Run “weighted” ANOVA  Mplus code  SPSS code  Output  Practice: 1 to 6 traj solutions

Exporting probabilites

Transposing

Practice 4  Run basic GMM with starting values  Save data  Import to SPSS  Transpose  Merge with original SPSS data file  Weight by PROB  Run frequency on TRAJ

Outline  Basic unconditional GMM  Introduction  Mplus code  Output and graphs  Conditional GMM (predictor)  Introduction  Mplus code  Output  Class-specific variance?  Introduction  Output and graphs  Exporting probabilities  Transpose file  Merge with data file  Run “weighted” ANOVA  Mplus code  SPSS code  Output  Practice: 1 to 6 traj solutions

End